-
公开(公告)号：US09170840B2
公开(公告)日：2015-10-27
申请号：US13287691
申请日：2011-11-02
CPC分类号： G06F9/4881
摘要： Duration sensitive scheduling in a computing environment, the computing environment including a computer configured to support a virtual machine, including: identifying, by a duration sensitive scheduler, a processing job to be executed by the virtual machine, wherein the virtual machine includes an entitlement specification that identifies physical resources of the computer that are designated for exclusive use by the virtual machine; determining, by the duration sensitive scheduler, a duration required to complete the processing job; identifying, by the duration sensitive scheduler, a time slot at which the physical resources of the computer that are identified in the entitlement specification are available for use by the virtual machine; scheduling, by the duration sensitive scheduler, the processing job for execution on the virtual machine during the time slot at which the physical resources of the computer that are identified in the entitlement specification are available for use by the virtual machine.
摘要翻译： 计算环境中的持续时间敏感调度，所述计算环境包括被配置为支持虚拟机的计算机，所述计算机配置为支持虚拟机，所述计算机环境包括：通过所述持续敏感调度器识别要由所述虚拟机执行的处理作业，其中所述虚拟机包括授权规范 其识别被虚拟机专用的计算机的物理资源; 由持续敏感调度器确定完成处理作业所需的持续时间; 通过持续时间敏感的调度器识别在授权规范中识别的计算机的物理资源可供虚拟机使用的时隙; 由所述持续时间敏感调度器调度在所述虚拟机期间在所述授权规范中识别的所述计算机的所述物理资源可供所述虚拟机使用的所述时隙期间执行所述处理作业。
-
2.发明授权Migrating virtual machines among networked servers upon detection of degrading network link operation 有权检测到网络链路运行恶化后，在网络服务器之间迁移虚拟机公开(公告)号：US08224957B2
公开(公告)日：2012-07-17
申请号：US12784061
申请日：2010-05-20
IPC分类号： G06F15/173 , G06F12/00
CPC分类号： G06F9/5088 , G06F9/5077 , G06F11/1484 , G06F11/202 , H04L67/101 , H04L67/34 , Y02D10/22 , Y02D10/32 , Y02D10/36
摘要： Migrating virtual machines among networked servers, the servers coupled for data communications with a data communications network that includes a networking device, where migrating includes: establishing, by a virtual machine management module (‘VMMM’), one or more virtual machines on a particular server; querying, by the VMMM, the networking device for link statistics of a link coupling the network device to the particular server for data communications; determining, by the VMMM in dependence upon the link statistics, whether the link coupling the network device to the particular server is degrading; and if the link coupling the network device to the particular server is degrading, migrating a virtual machine executing on the particular server to a destination server. In some embodiments, migrating occurs is carried out only if non-degrading link is available. If no non-degrading links are available, the network device, rather than the link, may be failing.
摘要翻译： 在网络服务器之间迁移虚拟机，这些服务器与数据通信网络（包括网络设备）进行数据通信，其中迁移包括：由虚拟机管理模块（“VMMM”）建立一个或多个虚拟机 服务器; 通过VMMM查询网络设备，用于将网络设备耦合到特定服务器以进行数据通信的链路的链路统计; 通过VMMM根据链路统计确定将网络设备耦合到特定服务器的链路是否恶化; 并且如果将网络设备耦合到特定服务器的链路正在降级，则将在特定服务器上执行的虚拟机迁移到目的地服务器。 在一些实施例中，只有在非降级链路可用时才进行迁移。 如果没有不降级的链接可用，则网络设备而不是链接可能会失败。
-
公开(公告)号：US20120069032A1
公开(公告)日：2012-03-22
申请号：US12885132
申请日：2010-09-17
CPC分类号： G06F9/45558 , G06F3/1454 , G06F2009/4557 , G06T1/20 , G09G5/363 , G09G2370/022
摘要： Methods, systems, and computer program products are provided for optimizing virtual graphics processing unit utilization. Embodiments include assigning a computing intensity level to each virtual machine of a plurality of virtual machines; assigning a priority level to each virtual machine of the plurality of virtual machines; determining for each server of a plurality of servers whether the server includes a virtual graphics processing unit (VGPU) that is available to perform compute intensive tasks for the plurality of virtual machines; and assigning one or more VGPUs to a virtual machine of the plurality of virtual machines in dependence upon the computing intensity level and the priority level of the virtual machine and the number of VGPUs available to perform the compute intensive tasks.
摘要翻译： 提供了方法，系统和计算机程序产品，用于优化虚拟图形处理单元利用率。 实施例包括将计算强度级别分配给多个虚拟机的每个虚拟机; 为所述多个虚拟机中的每个虚拟机分配优先级; 确定多个服务器的每个服务器，该服务器是否包括可用于为多个虚拟机执行计算密集型任务的虚拟图形处理单元（VGPU）; 以及根据计算强度级别和虚拟机的优先级级别以及可用于执行计算密集型任务的VGPU的数量，将一个或多个VGPU分配给多个虚拟机的虚拟机。
-
公开(公告)号：US09727360B2
公开(公告)日：2017-08-08
申请号：US13523003
申请日：2012-06-14
CPC分类号： G06F9/45558 , G06F3/1454 , G06F2009/4557 , G06T1/20 , G09G5/363 , G09G2370/022
摘要： Methods, systems, and computer program products are provided for optimizing virtual graphics processing unit utilization. Embodiments include assigning a computing intensity level to each virtual machine of a plurality of virtual machines; assigning a priority level to each virtual machine of the plurality of virtual machines; determining for each server of a plurality of servers whether the server includes a virtual graphics processing unit (VGPU) that is available to perform compute intensive tasks for the plurality of virtual machines; and assigning one or more VGPUs to a virtual machine of the plurality of virtual machines in dependence upon the computing intensity level and the priority level of the virtual machine and the number of VGPUs available to perform the compute intensive tasks.
-
公开(公告)号：US09348653B2
公开(公告)日：2016-05-24
申请号：US13483411
申请日：2012-05-30
CPC分类号： G06F9/5088 , G06F9/5077 , H04L67/1008 , H04L67/34
摘要： Virtual machine management among networked servers coupled for data communications with a data communications network that includes a network device and a Virtual Machine Management Module (‘VMMM’), where VM management includes: monitoring, by the network device, network traffic of applications executing in virtual machines of the servers; determining, in dependence upon the monitored network traffic, whether a particular application's network traffic exceeds a predetermined threshold, the particular application executing in a particular virtual machine of a particular server; if the particular application's network traffic exceeds the predetermined threshold, allocating, by the VMMM, an additional virtual machine in a different server; and instantiating, by the VMMM, in the additional virtual machine at least one application.
-
公开(公告)号：US20130111470A1
公开(公告)日：2013-05-02
申请号：US13287691
申请日：2011-11-02
IPC分类号： G06F9/455
CPC分类号： G06F9/4881
摘要： Duration sensitive scheduling in a computing environment, the computing environment including a computer configured to support a virtual machine, including: identifying, by a duration sensitive scheduler, a processing job to be executed by the virtual machine, wherein the virtual machine includes an entitlement specification that identifies physical resources of the computer that are designated for exclusive use by the virtual machine; determining, by the duration sensitive scheduler, a duration required to complete the processing job; identifying, by the duration sensitive scheduler, a time slot at which the physical resources of the computer that are identified in the entitlement specification are available for use by the virtual machine; scheduling, by the duration sensitive scheduler, the processing job for execution on the virtual machine during the time slot at which the physical resources of the computer that are identified in the entitlement specification are available for use by the virtual machine.
摘要翻译： 计算环境中的持续时间敏感调度，所述计算环境包括被配置为支持虚拟机的计算机，所述计算机配置为支持虚拟机，所述计算机环境包括：通过所述持续敏感调度器识别要由所述虚拟机执行的处理作业，其中所述虚拟机包括授权规范 其识别被虚拟机专用的计算机的物理资源; 由持续敏感调度器确定完成处理作业所需的持续时间; 通过持续时间敏感的调度器识别在授权规范中识别的计算机的物理资源可供虚拟机使用的时隙; 由所述持续时间敏感调度器调度在所述虚拟机期间在所述授权规范中识别的所述计算机的所述物理资源可供所述虚拟机使用的所述时隙期间执行所述处理作业。
-
公开(公告)号：US09733963B2
公开(公告)日：2017-08-15
申请号：US12885132
申请日：2010-09-17
CPC分类号： G06F9/45558 , G06F3/1454 , G06F2009/4557 , G06T1/20 , G09G5/363 , G09G2370/022
摘要： Methods, systems, and computer program products are provided for optimizing virtual graphics processing unit utilization. Embodiments include assigning a computing intensity level to each virtual machine of a plurality of virtual machines; assigning a priority level to each virtual machine of the plurality of virtual machines; determining for each server of a plurality of servers whether the server includes a virtual graphics processing unit (VGPU) that is available to perform compute intensive tasks for the plurality of virtual machines; and assigning one or more VGPUs to a virtual machine of the plurality of virtual machines in dependence upon the computing intensity level and the priority level of the virtual machine and the number of VGPUs available to perform the compute intensive tasks.
-
8.发明授权Migrating virtual machines among networked servers upon detection of degrading network link operation 有权检测到网络链路运行恶化后，在网络服务器之间迁移虚拟机公开(公告)号：US08495208B2
公开(公告)日：2013-07-23
申请号：US13462900
申请日：2012-05-03
CPC分类号： G06F9/5088 , G06F9/5077 , G06F11/1484 , G06F11/202 , H04L67/101 , H04L67/34 , Y02D10/22 , Y02D10/32 , Y02D10/36
摘要： Migrating virtual machines among networked servers, the servers coupled for data communications with a data communications network that includes a networking device, where migrating includes: establishing, by a virtual machine management module (‘VMMM’), one or more virtual machines on a particular server; querying, by the VMMM, the networking device for link statistics of a link coupling the network device to the particular server for data communications; determining, by the VMMM in dependence upon the link statistics, whether the link coupling the network device to the particular server is degrading; and if the link coupling the network device to the particular server is degrading, migrating a virtual machine executing on the particular server to a destination server. In some embodiments, migrating occurs is carried out only if non-degrading link is available. If no non-degrading links are available, the network device, rather than the link, may be failing.
摘要翻译： 在网络服务器之间迁移虚拟机，这些服务器与数据通信网络（包括网络设备）进行数据通信，其中迁移包括：由虚拟机管理模块（“VMMM”）建立一个或多个虚拟机 服务器; 通过VMMM查询网络设备，用于将网络设备耦合到特定服务器以进行数据通信的链路的链路统计; 通过VMMM根据链路统计确定将网络设备耦合到特定服务器的链路是否恶化; 并且如果将网络设备耦合到特定服务器的链路正在降级，则将在特定服务器上执行的虚拟机迁移到目的地服务器。 在一些实施例中，只有在非降级链路可用时才进行迁移。 如果没有不降级的链接可用，则网络设备而不是链接可能会失败。
-
公开(公告)号：US20120254868A1
公开(公告)日：2012-10-04
申请号：US13523003
申请日：2012-06-14
IPC分类号： G06F9/455
CPC分类号： G06F9/45558 , G06F3/1454 , G06F2009/4557 , G06T1/20 , G09G5/363 , G09G2370/022
摘要： Methods, systems, and computer program products are provided for optimizing virtual graphics processing unit utilization. Embodiments include assigning a computing intensity level to each virtual machine of a plurality of virtual machines; assigning a priority level to each virtual machine of the plurality of virtual machines; determining for each server of a plurality of servers whether the server includes a virtual graphics processing unit (VGPU) that is available to perform compute intensive tasks for the plurality of virtual machines; and assigning one or more VGPUs to a virtual machine of the plurality of virtual machines in dependence upon the computing intensity level and the priority level of the virtual machine and the number of VGPUs available to perform the compute intensive tasks.
-
10.发明申请Migrating Virtual Machines Among Networked Servers Upon Detection Of Degrading Network Link Operation 有权网络服务器中虚拟机迁移时，检测到网络链路运行失败公开(公告)号：US20120221887A1
公开(公告)日：2012-08-30
申请号：US13462900
申请日：2012-05-03
CPC分类号： G06F9/5088 , G06F9/5077 , G06F11/1484 , G06F11/202 , H04L67/101 , H04L67/34 , Y02D10/22 , Y02D10/32 , Y02D10/36
摘要： Migrating virtual machines among networked servers, the servers coupled for data communications with a data communications network that includes a networking device, where migrating includes: establishing, by a virtual machine management module (‘VMMM’), one or more virtual machines on a particular server; querying, by the VMMM, the networking device for link statistics of a link coupling the network device to the particular server for data communications; determining, by the VMMM in dependence upon the link statistics, whether the link coupling the network device to the particular server is degrading; and if the link coupling the network device to the particular server is degrading, migrating a virtual machine executing on the particular server to a destination server. In some embodiments, migrating occurs is carried out only if non-degrading link is available. If no non-degrading links are available, the network device, rather than the link, may be failing.
摘要翻译： 在网络服务器之间迁移虚拟机，这些服务器与数据通信网络（包括网络设备）进行数据通信，其中迁移包括：由虚拟机管理模块（“VMMM”）建立一个或多个虚拟机 服务器; 通过VMMM查询网络设备，用于将网络设备耦合到特定服务器以进行数据通信的链路的链路统计; 通过VMMM根据链路统计确定将网络设备耦合到特定服务器的链路是否恶化; 并且如果将网络设备耦合到特定服务器的链路正在降级，则将在特定服务器上执行的虚拟机迁移到目的地服务器。 在一些实施例中，只有在非降级链路可用时才进行迁移。 如果没有不降级的链接可用，则网络设备而不是链接可能会失败。
-
-
-
-
-
-
-
-
-
搜索结果
17 条记录 (耗时 0.022 秒)
